[PPT] - Applied Machine Learning Introduction 1 APPLIED MACHINE LEARNING PowerPoint Presentation

SLIDE 1

APPLIED MACHINE LEARNING

1

Applied Machine Learning Introduction

SLIDE 2

APPLIED MACHINE LEARNING

Practicalities

Slides and exercises will be posted on the website of the class the day before class:

http://lasa.epfl.ch/teaching/lectures/ML_Msc/index.php

http://lasa.epfl.ch/  Teaching  Lectures  Applied Machine Learning

Solutions to the exercises will be posted a week after the exercise session.

SLIDE 3

APPLIED MACHINE LEARNING

Practicalities Contact Information of the Instructors

SLIDE 4

APPLIED MACHINE LEARNING

4

Class Format

Lectures with interactive exercises: 9h15-12h00
Exercises (In class): 12h15-13h00
Lectures alternates with Practical session held in

C06-C04, see class schedule! ! Practical sessions run from 8h00 to 13h00 with one hour break 10h00-11h00.

Attendance to practical and exercise sessions is highly

recommended….

SLIDE 5

APPLIED MACHINE LEARNING

5

Grading Scheme

Practicals (25% of the grade) – done in team of 2 1 report – due 16/12/2016

r

1 oral presentation – December 16/12/2016 Register on doodle links on class website! Written Exam (75% of the grade) 3 hours long Closed book Allowed 1 A4 pages with handwritten notes

SLIDE 6

APPLIED MACHINE LEARNING

6

LASA

SLIDE 7

APPLIED MACHINE LEARNING

7

Pre-requisites

Linear Algebra  Vector / Matrix notation  Eigenvalue decomposition  Linear dependency Probability / Statistics  Probability Distribution Function  Covariance, Expectation  Joint, conditional probability  Correlation / Statistical Independence Optimization  Global versus local optima  Gradient descent  Method of Lagrange Multipliers

Brief recap of main algorithms in class

SLIDE 8

APPLIED MACHINE LEARNING

8

To understand the basics of some key algorithms of Machine

Learning

To apply some of these algorithms with real data and, by so

doing, to understand the limitations of the algorithm for real- time systems

To raise in you enough interest for the field, so that you will

later try to learn more about it (advanced class at the doctoral school, search on-line, …)

To have more engineers apply these techniques for robust

control, signal processing, prediction, learning, etc.

Class Objectives

SLIDE 9

APPLIED MACHINE LEARNING

9

Main learning outcomes: By the end of the course, the student must be able to:

Choose an appropriate ML method
Assess / Evaluate an appropriate ML method
Apply an appropriate ML method

Transversal skills

Write a scientific or technical report.
Make an oral presentation.

Learning Outcomes

SLIDE 10

APPLIED MACHINE LEARNING

10

Today’s class format

Taxonomy and basic concepts in ML + examples
f ML applications
Introduction to Principal Component Analysis

SLIDE 11

APPLIED MACHINE LEARNING

Data Mining

Pattern recognition with very large amount of high-dimensional data

(Tens of thousands to billions) (Several hundreds and more)

SLIDE 12

APPLIED MACHINE LEARNING

Data Mining: examples

Other algorithms required:  Fast methods for crawling the web  Text processing (Natural Language Processing)  Understanding semantics Mining webpages

Cluster groups of webpage by topics
Cluster links across webpages

Issues:

Domain-specific language / terminology
Foreign languages
Dynamics of web (pages disappear / get created)

SLIDE 13

APPLIED MACHINE LEARNING

13

Machine Learning: definitions

Machine Learning is the field of scientific study that concentrates on induction algorithms and on other algorithms that can be said to ``learn.''

Machine Learning Journal, Kluwer Academic

Machine Learning is an area of artificial intelligence involving developing techniques to allow computers to “learn”. More specifically, machine learning is a method for creating computer programs by the analysis of data sets, rather than the intuition of engineers. Machine learning

verlaps heavily with statistics, since both fields study the analysis of
data. Webster Dictionary

Machine learning is a branch of statistics and computer science, which studies algorithms and architectures that learn from data sets. WordIQ

SLIDE 14

APPLIED MACHINE LEARNING

14

What is Machine Learning?

Machine Learning encompasses a large set of algorithms that aim at inferring information from what is hidden.

A. M. Bronstein, M. M. Bronstein, M. Zibulevsky, "On separation of semitransparent dynamic images from static background", Proc. Intl. Conf. on Independent Component Analysis

and Blind Signal Separation, pp. 934-940, 2006.

Independent Component Analysis (ICA) can decompose mixture of signals

SLIDE 15

APPLIED MACHINE LEARNING

15

What is Machine Learning?

Helps compute automatically information that would take days to do by hand.

Noris, B., Nadel, J, Barker, M., Hadjikhani, N. and Billard, A. (2012) Investigating gaze of children with ASD in naturalistic settings. PLOS ONE.

The mapping can be done through support vector regression  An algorithm we will see in class

SLIDE 16

APPLIED MACHINE LEARNING

16

What is Machine Learning?

Recognizing human speech. Here this the wave produced when uttering the word “allright”. The strength of ML algorithms is that they can apply to arbitrary set of data. It can recognizing patterns from what from various source of data. Modeling time series: Hidden Markov Models be used to recognize complex sounds, including human speech.

SLIDE 17

APPLIED MACHINE LEARNING

17

What is Machine Learning?

Piano note (C5 – do) Same note played by a oboe (hautbois)

Classification: Two patterns that are different should still be grouped in the same class

SLIDE 18

APPLIED MACHINE LEARNING

18

Why and when do we need learning in Robotics?

SLIDE 19

APPLIED MACHINE LEARNING

19

Peg and Hole Problem

A typical problem of Robotics

SLIDE 20

APPLIED MACHINE LEARNING

20

A typical problem of Robotics

Peg and Hole Problem

SLIDE 21

APPLIED MACHINE LEARNING

21

A: Engineer the environment

A typical problem of Robotics

SLIDE 22

APPLIED MACHINE LEARNING

22

A: Engineer the environment B: Engineer the body

A typical problem of Robotics

SLIDE 23

APPLIED MACHINE LEARNING

23

A: Engineer the environment B: Engineer the body C: Engineer the controller Systematic search  Adaptive control  Learning Machine!

A typical problem of Robotics

SLIDE 24

APPLIED MACHINE LEARNING

24

To engineer the environment is not always desirable Rather, it is desirable to have a system that is Adaptable to different environments That can generalize across tasks

Kronander, Burdet and Billard, Learning PegI n Hole Insertionf rom Human Demonstrations, 2013

SLIDE 25

APPLIED MACHINE LEARNING

25

Problem

A: Engineer the environment B: Engineer the body C: Engineer the controller ROWS 4-6 Make an autonomous robot that cleans dirty dishes in the cafeteria ROWS 1-3 Make an autonomous robot that distributes graded assignments to a class of students

SLIDE 26

APPLIED MACHINE LEARNING

26

To engineer the environment is not always desirable Rather, it is desirable to have a system that is adaptable to different environments can generalize across tasks

Machines that learn

SLIDE 27

APPLIED MACHINE LEARNING

27

Supervised learning – where the algorithm learns a function or

model that maps a set of inputs to a set of desired outputs.

Unsupervised learning – where the algorithm learns a model that

represents a set of inputs without any feedback (no desired output, no external reinforcement).

Reinforcement learning –

where the algorithm learns a mechanism that generates a set of outputs from one input in order to maximize a reward value (external and delayed feedback).

Taxonomy in ML

SLIDE 28

APPLIED MACHINE LEARNING

28

Supervised learning relates to a vast group of methods by

which one estimates a model from a set of examples,  The system is given the desired output.

When these examples are provided by a human expert,

this is referred to robot learning from demonstration; robot programming by demonstration.

Supervised learning

SLIDE 29

APPLIED MACHINE LEARNING

29

Noris, B., Nadel, J, Barker, M., Hadjikhani, N. and Billard, A. (2012) Investigating gaze of children with ASD in naturalistic settings. PLOS ONE.

Supervised learning

Where do the eyes look? Map image of the eyes to point in the camera image

SLIDE 30

APPLIED MACHINE LEARNING

30

What is sometimes impossible to see for humans is easy for ML to pick.

Noris, B., Keller, J-B. and Billard, A. (2011) A Wearable Gaze Tracking System for Children in Unconstrained Environments. Computer Vision and Image Understanding.

Exploit information not only on the pupil, cornea, but also on wrinkles, eyelids and eyelashed pattern to infer gaze direction.

Support Vector Regression can be used to learn this mapping

Supervised learning

SLIDE 31

APPLIED MACHINE LEARNING

31

Noris, B., Keller, J-B. and Billard, A. (2011) A Wearable Gaze Tracking System for Children in Unconstrained Environments. Computer Vision and Image Understanding.

Support Vector Regression can be used to learn this mapping

20 20,

1...50

i x

x i  

Input: 50 images of the eyes, In grey color 20x20 pixels Output: 50 images of the scene, In grey color 240x320 pixels

 

y f x 

240 320,

1...50

i x

y i  

Learn a function f:

Supervised learning

SLIDE 32

APPLIED MACHINE LEARNING

32

Unsupervised Learning

Unsupervised learning refers to a variety of methods by which a pair of signals y and x are associated but there is no explicit labeling as to which y should be associated to which x. This is often done through association, i.e. through associative learning.

SLIDE 33

APPLIED MACHINE LEARNING

33

Associative Learning for Learning Word-Objects Relations

H. Kozima, H. Yano, A robot that learns to communicate with human caregivers, in: Proceedings of the International

Workshop on Epigenetic Robotics, 2001

SLIDE 34

APPLIED MACHINE LEARNING

34

Reinforcement Learning (RL)

RL tries to infer the optimal path to the goal, through a process of Trial-and-error, so as to maximize the reward. Reinforcement learning is a tedious learning method. It is slow and is functional only in well-defined problems with small search space.

SLIDE 35

APPLIED MACHINE LEARNING

35

Reinforcement Learning

Robotics Applications

Atkeson & Schaal, Learning how to swing an inverted pendulum, ICRA 1997.

The robot tracks the position of the two colored ball. Using a model of the inverse pendulum dynamics, it learns which joint angle displacement to produce to ensures that the ball remains in equilibrium.

SLIDE 36

APPLIED MACHINE LEARNING

36

Summary

Machine Learning encompasses a large area of works which cannot all be covered here. We will focus on a subset of algorithms that form the foundation of most current advances in machine learning. We however omit topics. Some of these are covered in other courses on machine learning at EPFL.

SLIDE 37

APPLIED MACHINE LEARNING

37

Some Machine Learning Resources

On-line resources:

http://www.machinelearning.org/index.html
http://www.pascal-network.org/ Network of excellence on Pattern Recognition, Statistical Modelling

and Computational Learning (summer schools and workshops)

Journals:

Machine Learning Journal, Kluwer Publisher
IEEE Transactions on Signal processing
IEEE Transactions on Pattern Analysis
IEEE Transactions on Pattern Recognition
The Journal of Machine Learning Research

Conferences:

ICML: int. conf. on machine learning
Neural Information Processing Conference – on-line repository of all research papers,